Publications
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Zuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu, Ding Zhao, Shoham Sabach, Rasool Fakoor
ICLR 2024. [PDF]
Time-Varying Propensity Score to Bridge the Gap between the Past and Present
Rasool Fakoor, Jonas Mueller, Zachary C. Lipton, Pratik Chaudhari, Alexander J. Smola
ICLR 2024. [PDF]
Learning the Target Network in Function Space
Kavosh Asadi*, Yao Liu*, Shoham Sabach*, Ming Yin*, Rasool Fakoor
ICML 2024. [PDF]
Resetting the Optimizer in Deep RL: An Empirical Study
Kavosh Asadi, Rasool Fakoor, Shoham Sabach
NeurIPS 2023. [PDF]
TD Convergence: An Optimization Perspective
Kavosh Asadi, Shoham Sabach, Yao Liu, Omer Gottesman, Rasool Fakoor
NeurIPS 2023. [PDF]
Adaptive Interest for Emphatic Reinforcement Learning
Martin Klissarov, Rasool Fakoor, Jonas Mueller, Kavosh Asadi, Taesup Kim, Alexander J. Smola
NeurIPS 2022 . [PDF]
Robust Reinforcement Learning for Shifting Dynamics During Deployment
Samuel Stanton, Rasool Fakoor, Jonas Mueller, Andrew Gordon Wilson, Alexander J. Smola
Safe and Robust Control of Uncertain Systems Workshop, NeurIPS 2021. [PDF]
TraDE: Transformers for Density Estimation
Rasool Fakoor, Pratik Chaudhari, Jonas Mueller, Alexander J. Smola.
Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models Workshop, ICML 2020. [PDF]
DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning
Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola.
Preprint 2020. [PDF]
P3O: Policy-on Policy-off Policy Optimization
Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola.
UAI 2019. [PDF][Code]
Also, second place in sample-efficiency track of ProcGen competition at NeurIPS 2020
Constrained Convolutional-Recurrent Networks to Improve Speech Quality with Low Impact on Recognition Accuracy
Rasool Fakoor, Xiaodong He, Ivan Tashev, Shuayb Zarar.
ICASSP 2018 . [PDF]
Differentiable Greedy Networks
Thomas Powers, Rasool Fakoor, Siamak Shakeri, Abhinav Sethy, Amanjit Kainth, Abdel-rahman Mohamed, Ruhi Sarikaya.
ArXiv, Oct 2018. [PDF]
Reinforcement Learning To Adapt Speech Enhancement to Instantaneous Input Signal Quality
Rasool Fakoor, Xiaodong He, Ivan Tashev, Shuayb Zarar.
NIPS 2017, Machine Learning for Audio Signal Processing Workshop, December 2017. [PDF]
Deep Transferable Zero-shot Learning with Layer-specific Regularizers and Embeddings
Rasool Fakoor, Mohit Bansal, Matthew R. Walter.
Technical Report, December 2015. [PDF]
Deep Attribute-based Zero-shot Learning with Layer-specific Regularizers
Rasool Fakoor, Mohit Bansal, Matthew R. Walter.
NIPS 2015, Transfer and Multi-Task Learning Workshop, December 2015. [PDF]
A Sampling-Based Approach to Reducing the Complexity of Continuous State Space POMDPs by Decomposition into Coupled Perceptual and Decision Processes.
Rasool Fakoor, Manfred Huber.
The 11th International Conference on Machine Learning and Applications (ICMLA 2012). December 2012.
[PDF]
Improving Tractability of POMDPs by Separation of Decision and Perceptual Processes.
Rasool Fakoor, Manfred Huber.
The 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2012), October 2012.
[PDF]
An Integrated Cloud-based Framework for Mobile Phone Sensing.
Rasool Fakoor, Mayank Raj, Azade Nazi, Mario Di Francesco, S. K. Das.
Proceedings of the ACM SIGCOMM, Workshop on Mobile Cloud Computing (MCC 2012), August 2012.
[PDF]
Reducing the complexity of reinforcement learning in POMDPs by decomposition into decision and perceptual processes.
Rasool Fakoor.
Master Thesis, December 2012. [PDF]